Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification

11 July 2020

Papers citing "Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification"

8 / 8 papers shown

Title
Adversarially trained neural representations may already be as robust as corresponding biological neural representations Chong Guo Michael J. Lee Guillaume Leclerc Joel Dapello Yug Rao A. Madry J. DiCarlo GAN AAML 11 13 0 19 Jun 2022
Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis Yaogong Feng Xiaowen Huang Pengbo Yang Jian Yu Jitao Sang DiffM 19 29 0 10 Mar 2022
Adversarial Training Helps Transfer Learning via Better Representations Zhun Deng Linjun Zhang Kailas Vodrahalli Kenji Kawaguchi James Y. Zou GAN 36 52 0 18 Jun 2021
Unsupervised Robust Domain Adaptation without Source Data Peshal Agarwal D. Paudel Jan-Nico Zaech Luc Van Gool OOD TTA 21 27 0 26 Mar 2021
Adversarial Training is Not Ready for Robot Learning Mathias Lechner Ramin Hasani Radu Grosu Daniela Rus T. Henzinger AAML 19 34 0 15 Mar 2021
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 19 48 0 19 Oct 2020
Do Adversarially Robust ImageNet Models Transfer Better? Hadi Salman Andrew Ilyas Logan Engstrom Ashish Kapoor A. Madry 32 416 0 16 Jul 2020
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability Kaizhao Liang Jacky Y. Zhang Boxin Wang Zhuolin Yang Oluwasanmi Koyejo B. Li AAML 15 25 0 25 Jun 2020